Instructions to use rzgar/Eva-Qwen-Flat-Chest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rzgar/Eva-Qwen-Flat-Chest with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2512", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("rzgar/Eva-Qwen-Flat-Chest") prompt = "Strength: 0.33 | Eva Qwen V4b LoRA Strength: 0.94" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Eva Qwen Flat Chest

- Prompt
- Strength: 0.33 | Eva Qwen V4b LoRA Strength: 0.94

- Prompt
- Strength: 0.36

- Prompt
- Strength: 0.36

- Prompt
- Strength: 0.43

- Prompt
- Strength: 0.75 | Base model JIB Mix Qwen V6

- Prompt
- Strength: 0.70 | Base model JIB Mix Qwen V6
Model description
A specialized LoRA that gives you flat chest and breast sizes (controled by LoRA strength) when used together with the Eva Qwen character LoRA series.
It also can be used as a standalone LoRA, defaulting to slim bodie with completely flat chests.
> Trained entirely on close-up, upper-body, and full-body nude images.
With Eva Qwen Character LoRAs (Recommended)
| Setting | Recommended Value | Notes |
|---|---|---|
| LoRA Strength | 0.2 – 0.33 | Safe zone |
| Higher Strength | > 0.5 | Progressively reduces clothing / increases nudity |
For prompts involving nudity or sexual content, pair this LoRA with one of the following:
| LoRA | Description | Download Link |
|---|---|---|
| Eva Qwen V3 | Best NSFW performance among all Eva Qwen versions | Eva_Qwen_V3.safetensors |
| META4 | Merge of 4 Qwen-Image NSFW beta LoRAs | Meta4.safetensors |
Post-processing tips:
- SDXL Refiner -> noticeably improves quality and anatomy
- WAN 2.2 -> fixes slightly deformed genitals in first 3 or 5 frames (both male & female) when using NSFW merges
Recommended Checkpoints & Accelerators
| Component | Recommendation | Link |
|---|---|---|
| Main Checkpoint (FP8) | Jib Mix Qwen v6 | Download |
| 8-Step Lightning LoRA | Qwen-Image-2512-Lightning-8steps-V1.0-fp32 | Download |
Trigger words
You should use Eva_Flat_Chest to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 33
Model tree for rzgar/Eva-Qwen-Flat-Chest
Base model
Qwen/Qwen-Image-2512